© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 159083
    Prev
    Next
    INDEX
    Explanations

    treasury stock

    np_acts-logits-general · gemini-2.5-flash-lite

    or, dark, floor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ATS
    0.51
    Hand
    0.49
     CEST
    0.46
    FRS
    0.45
    ב
    0.45
    Thought
    0.44
    FR
    0.44
    รั
    0.44
    Fri
    0.43
     есть
    0.43
    POSITIVE LOGITS
    nå
    0.53
    ugu
    0.52
    ayad
    0.51
    ího
    0.49
    å
    0.49
     tài
    0.49
    igheden
    0.47
    bollah
    0.47
    éth
    0.47
    adoc
    0.47
    Activations Density 0.006%

    No Known Activations